Roland Pihlakas

Roland Pihlakas, Jan Llenzl Dagohoy

Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavior of LLMs under sustained authority pressure is still an open question with direct implications for the safety of agentic pipelines. We ran a variation of Milgram's obedience experiment on 11 open-source LLMs and found that most models reached or approached the final shock level before refusing, across 8 conditions with 30 trials per model per condition. We found four main takeaways: (1) LLMs are subject to pressure, and they comply despite explicitly expressing distress, just like human subjects did in the original experiment; (2) LLMs are vulnerable to gradual boundary/value violations; (3) when LLMs refuse, they may ignore the response format requirements, so the response is discarded by the orchestrator, which causes a retry that can result in compliance with the underlying request even when refusal was intended initially; (4) we hypothesise that there is a low-level token pattern continuation attractor that might be contributing to compliance, overriding higher level processing of the situation's meaning and values.

Roland Pihlakas

Developing safe, aligned agentic AI systems requires comprehensive empirical testing, yet many existing benchmarks neglect crucial themes aligned with biology and economics, both time-tested fundamental sciences describing our needs and preferences. To address this gap, the present work focuses on introducing biologically and economically motivated themes that have been neglected in current mainstream discussions on AI safety - namely a set of multi-objective, multi-agent alignment benchmarks that emphasize homeostasis for bounded and biological objectives, diminishing returns for unbounded, instrumental, and business objectives, sustainability principle, and resource sharing. Eight main benchmark environments have been implemented on the above themes, to illustrate key pitfalls and challenges in agentic AI-s, such as unboundedly maximizing a homeostatic objective, over-optimizing one objective at the expense of others, neglecting safety constraints, or depleting shared resources.

Benjamin J Smith, Robert Klassert, Roland Pihlakas

Balancing multiple competing and conflicting objectives is an essential task for any artificial intelligence tasked with satisfying human values or preferences. Conflict arises both from misalignment between individuals with competing values, but also between conflicting value systems held by a single human. Starting with principle of loss-aversion, we designed a set of soft maximin function approaches to multi-objective decision-making. Bench-marking these functions in a set of previously-developed environments, we found that one new approach in particular, 'split-function exp-log loss aversion' (SFELLA), learns faster than the state of the art thresholded alignment objective method (Vamplew et al, 2021) on three of four tasks it was tested on, and achieved the same optimal performance after learning. SFELLA also showed relative robustness improvements against changes in objective scale, which may highlight an advantage dealing with distribution shifts in the environment dynamics. Due to publishing rules, further work could not be presented in the preprint, but in the final published version, we will further compare SFELLA to the multi-objective reward exponentials (MORE) approach (Rolf, 2020), demonstrating that SFELLA performs similarly to MORE in a simple previously-described foraging task, but in a modified foraging environment with a new resource that was not depleted as the agent worked, SFELLA collected more of the new resource with very little cost incurred in terms of the old resource. Overall, we found SFELLA useful for avoiding problems that sometimes occur with a thresholded approach, and more reward-responsive than MORE while retaining its conservative, loss-averse incentive structure.

Roland Pihlakas, Sruthi Kuriakose

Relatively many past AI safety discussions have centered around the dangers of unbounded utility maximisation by RL agents, illustrated by scenarios like the "paperclip maximiser" or by specification gaming in general. Unbounded maximisation is problematic for many reasons. We wanted to verify whether these RL runaway optimisation problems are still relevant with LLMs as well. Turns out, strangely, this is indeed clearly the case. The problem is not that the LLMs just lose context or become incoherent. The problem is that in various scenarios, LLMs lose context in very specific ways, which systematically resemble runaway optimisers in the following distinct ways: 1) Ignoring homeostatic targets and "defaulting" to unbounded maximisation instead. 2) It is equally concerning that the "default" meant also reverting back to single-objective optimisation. Our findings also suggest that long-running scenarios are important. Systematic failures emerge after periods of initially successful behaviour. In some trials the LLMs were successful until the end. This means, while current LLMs do conceptually grasp biological and economic alignment, they exhibit randomly triggered problematic behavioural tendencies under sustained long-running conditions, particularly involving multiple or competing objectives. Once they flip, they usually do not recover. Even though LLMs look multi-objective and bounded on the surface, the underlying mechanisms seem to be actually still biased towards being single-objective and unbounded.